Copertina

Iterative Refinement Improves Compositional Image Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jaiswal, Shantanu, Prabhudesai, Mihir, Bhardwaj, Nikash, Qin, Zheyang, Zadeh, Amir, Li, Chuan, Fragkiadaki, Katerina, Pathak, Deepak
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2026)

Video Diffusion Alignment via Reward Gradients
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2024)

Diffusion Beats Autoregressive in Data-Constrained Settings
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2025)

Aligning Text-to-Image Diffusion Models with Reward Backpropagation
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2023)

Unified Multimodal Discrete Diffusion
di: Swerdlow, Alexander, et al.
Pubblicazione: (2025)

Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
di: Kuang, Yuxuan, et al.
Pubblicazione: (2026)

RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph
di: Liu, Yifan, et al.
Pubblicazione: (2025)

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
di: Ke, Tsung-Wei, et al.
Pubblicazione: (2024)

Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
di: Shibata, Yuto, et al.
Pubblicazione: (2026)

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
di: Gkanatsios, Nikolaos, et al.
Pubblicazione: (2023)

DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
di: Xie, Guanghu, et al.
Pubblicazione: (2025)

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
di: Chen, Jiayi, et al.
Pubblicazione: (2026)

Video Generation with Learned Action Prior
di: Sarkar, Meenakshi, et al.
Pubblicazione: (2024)

Unifying 2D and 3D Vision-Language Understanding
di: Jain, Ayush, et al.
Pubblicazione: (2025)

EgoFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
di: Su, Haisheng, et al.
Pubblicazione: (2024)

RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
di: Wang, Yufei, et al.
Pubblicazione: (2023)

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
di: Hung, Chia-Yu, et al.
Pubblicazione: (2025)

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
di: Chu, Wen-Hsuan, et al.
Pubblicazione: (2024)

Maximizing Confidence Alone Improves Reasoning
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2025)

Self-Questioning Language Models
di: Chen, Lili, et al.
Pubblicazione: (2025)

IFG: Internet-Scale Guidance for Functional Grasping Generation
di: Liu, Ray Muxin, et al.
Pubblicazione: (2025)

Pose-Guided Residual Refinement for Interpretable Text-to-Motion Generation and Editing
di: Jeong, Sukhyun, et al.
Pubblicazione: (2025)

CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration
di: Yao, Gongxin, et al.
Pubblicazione: (2024)

Continuously Improving Mobile Manipulation with Autonomous Real-World RL
di: Mendonca, Russell, et al.
Pubblicazione: (2024)

ODIN: A Single Model for 2D and 3D Segmentation
di: Jain, Ayush, et al.
Pubblicazione: (2024)

Thermal Image Refinement with Depth Estimation using Recurrent Networks for Monocular ORB-SLAM3
di: Şahin, Hürkan, et al.
Pubblicazione: (2026)

ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation
di: Qin, Yiran, et al.
Pubblicazione: (2026)

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
di: Lin, Yuchen, et al.
Pubblicazione: (2025)

Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement
di: Zheng, Jiakun, et al.
Pubblicazione: (2026)

SAPG: Split and Aggregate Policy Gradients
di: Singla, Jayesh, et al.
Pubblicazione: (2024)

Improved Image-based Pose Regressor Models for Underwater Environments
di: Peng, Luyuan, et al.
Pubblicazione: (2024)

Local Policies Enable Zero-shot Long-horizon Manipulation
di: Dalal, Murtaza, et al.
Pubblicazione: (2024)

Improving Generalization of Language-Conditioned Robot Manipulation
di: Cui, Chenglin, et al.
Pubblicazione: (2025)

DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving
di: Godbole, Mihir, et al.
Pubblicazione: (2025)

Improving Zero-Shot ObjectNav with Generative Communication
di: Dorbala, Vishnu Sashank, et al.
Pubblicazione: (2024)

DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning
di: Swami, Kunal, et al.
Pubblicazione: (2025)

Improved Bag-of-Words Image Retrieval with Geometric Constraints for Ground Texture Localization
di: Wilhelm, Aaron, et al.
Pubblicazione: (2025)

ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
di: Bhardwaj, Arjun, et al.
Pubblicazione: (2026)

PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving
di: Chen, Zhili, et al.
Pubblicazione: (2023)

Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
di: Xu, Weisheng, et al.
Pubblicazione: (2026)